检索结果-内蒙古大学图书馆

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Anand, Ketan Dwivedi, Shyam Shankar Department of Computer Science and Engineering Rameshwaram Institute of Technology & Management AKTU Lucknow India

ISBN: (纸本)9798331530389

Modern intelligent transportation systems and autonomous driving technologies are quite helpful in light of the population's increasing growth, and they work particularly well when used in conjunction with traffic sign monitoring. By giving drivers accurate and exact traffic signals, such as speed limits, warnings, and directional assistance, this makes transportation much safer. Autonomous vehicles must correctly understand these indicators in order to make wise driving judgments. Accurately identifying and classifying a wide variety of traffic signs in a range of environmental circumstances is a difficulty. A cutting-edge deep learning model created specifically for object recognition tasks is called YOLOv9 (You Only Look Once version 9).In addition to offering respectable speed and accuracy, YOLOv9 expands on the advantages of its predecessors by implementing cutting-edge strategies such as PGI and *** of these improvements, YOLOv9 is especially ideal for real-time applications like recognition of traffic signs, where more accuracy and quick and accurate object identification are essential. With an increased accuracy the results demonstrate the model's stability and dependability and show that it is appropriate for real-world uses in autonomous driving and traffic control. Subsequent investigations will concentrate on improving resilience in various situations, utilizing semi-supervised learning, creating more resource-efficient models, broadening the range of datasets, and combining traffic sign recognition with additional autonomous driving tasks. The development of dependable and effective traffic sign detection systems is furthered by this work. © 2025 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A 0.75mm2407µW Real-Time Speech Audio Denoiser with Quantized Cascaded Redundant Convolutional Encoder-Decoder for Wearable IoT Devices 38

A 0.75mm2407µW Real-Time Speech Audio Denoiser with Quantiz...

引用

38th International Conference on VLSI Design, VLSID 2025

作者： Kochar, Dimple Vijay Ashok, Maitreyi Chandrakasan, Anantha P. Massachusetts Institute of Technology Electrical Engineering and Computer Science CambridgeMA United States

ISBN: (纸本)9798331522445

Audio denoising is crucial for delivering high-quality sound in applications ranging from communication devices to entertainment systems. On-device denoising is critical for en-suring consistent performance across various host platforms. Machine learning (ML) models exhibit strong audio processing performance in the frequency domain but require efficient hardware design. This paper focuses on enhancing audio quality using convolutional encoder-decoder ML models with low power consumption while meeting real-time processing constraints. We achieve this by developing a quantized network that optimally reduces computational costs without compromising enhancement quality. Furthermore, our hardware quantization scheme reduces memory usage by up to 75% while maintaining accuracy. Next, we design a complementary processing element activation routing scheme tailored to our algorithm, significantly reducing the on-chip memory accesses by 5-9×. Fabricated in 28nm CMOS process, our chip demonstrates real-time audio denoising, processing each frame within 8ms while consuming only 407µ or 3.24 µJ/frame at 0.65V, 18.5 MHz, making it ideal for battery-powered IoT devices. In terms of performance, our chip also achieves the highest evaluation score for audio quality (PESQ), outperforming previous works. © 2025 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Improvised Prediction of Rainfall using Random Forest Classifier over Taiwan 4

Improvised Prediction of Rainfall using Random Forest Classi...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Puttanapura, Jagadeshwari Monika Singh, T. Kishor Kumar Reddy, C. Doss, Srinath Stanley College of Engineering & Technology for Women Department of Computer Science and Engineering Hyderabad India Botho University Faculty of Engineering and Technology Botswana

ISBN: (纸本)9798331515720

Inadequate rainfall causes reduced harvesting, reduced availability of water, economic losses, environmental degradation, public health problems, decreased power generation, social unrest, and infrastructure destruction. Improved Rainfall prediction helps in better management of farming, resource allocation, scheduling, and disaster prevention. This leads to enhanced farming strategies, as well as more efficient water resource distribution and disaster preparedness. The dataset contains six weather variables including humidity, temperature, pressure, wind direction and speed. Numerous techniques, such as long short-Term memory (LSTM) model, bidirectional long short-Term memory (Bi-LSTM), Deep Learning Neural Networks (DLNN), Random Forest (RF), Artificial Neural Networks (ANN), K-Nearest Neighbor, Support Vector Machines (SVM), Logistic Regression were compared. The RF model's precision and accuracy were 86% and 96% respectively. In comparison with other models' performance, RF had the best outcomes. The results demonstrate that the RF algorithm can supply dependable meteorological forecasts. Such dependability is of use to farmers and other disaster response stakeholders, since it enhances planning and preparedness efforts through provision of reliable predictions. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Driven Inference Testing for Question Answering Software 24

Knowledge Graph Driven Inference Testing for Question Answer...

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Wang, Jun Li, Yanhui Chen, Zhifei Chen, Lin Zhang, Xiaofang Zhou, Yuming Nanjing University State Key Laboratory for Novel Software Technology China School of Computer Science and Engineering Nanjing University of Science and Technology China School of Computer Science and Technology Soochow University China

ISBN: (纸本)9798400702174

In the wake of developments in the field of Natural Language Processing, Question Answering (QA) software has penetrated our daily lives. Due to the data-driven programming paradigm, QA software inevitably contains bugs, i.e., misbehaving in real-world applications. Current testing techniques for testing QA software include two folds, reference-based testing and metamorphic testing. This paper adopts a different angle to achieve testing for QA software: we notice that answers to questions would have inference relations, i.e., the answers to some questions could be logically inferred from the answers to other questions. If these answers on QA software do not satisfy the inference relations, an inference bug is detected. To generate the questions with the inference relations automatically, we propose a novel testing method Knowledge Graph driven Inference Testing (KGIT), which employs facts in the Knowledge Graph (KG) as the seeds to logically construct test cases containing questions and contexts with inference relations. To evaluate the effectiveness of KGIT, we conduct an extensive empirical study with more than 2.8 million test cases generated from the large-scale KG YAGO4 and three QA models based on the state-of-the-art QA model structure. The experimental results show that our method (a) could detect a considerable number of inference bugs in all three studied QA models and (b) is helpful in retraining QA models to improve their inference ability. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Signal Conducting System with Effective Optimization Using Deep Learning for Schizophrenia Classification

引用

computer Systems science & engineering 2023年第5期45卷 1869-1886页

作者： V.Divya S.Sendil Kumar V.Gokula Krishnan Manoj Kumar School of Electrical and Electronics Engineering Sathyabama Institute of Science and TechnologyChennaiTamilnaduIndia Department of Electrical and Electronics Engineering S A Engineering CollegeChennaiTamilnaduIndia Department of Computer Science and Information Technology CVR College of EngineeringMangalpallyHyderabadTelanganaIndia School of Computer Science University of Petroleum and Energy StudiesDehradunIndia

Signal processing based research was adopted with Electroencephalogram(EEG)for predicting the abnormality and cerebral *** proposed research work is intended to provide an automatic diagnostic system to determine the EEG signal in order to classify the brain function which shows whether a person is affected with schizophrenia or *** detection and intervention are vital for better ***,the diagnosis of schizophrenia still depends on clinical observation to *** reliable biomarkers,schizophrenia is difficult to detect in its early phase and hence we have proposed this *** this work,the EEG signal series are divided into non-linear feature mining,classification and validation,and t-test integrated feature selection *** this work,19-channel EEG signals are utilized from schizophrenia class and normal ***,the datasets initially execute the splitting process based on raw 19-channel EEG into 6250 sample point’s *** this process,1142 features of normal and schizophrenia class patterns can be *** other hand,157 features from each EEG patterns are utilized based on Non-linear feature extraction process where 14 principal features can be identified in terms of considering the essential *** last,the Deep Learning(DL)technique incorporated with an effective optimization technique is adopted for classification process called a Deep Convolutional Neural Network(DCNN)with mayfly optimization *** proposed technique is implemented into the platform of MATLAB in order to obtain better results and is analyzed based on the performance analysis framework such as accuracy,Signal to Noise Ratio(SNR),Mean Square Error,Normalized Mean Square Error(NMSE)and *** comparison,the proposed technique is proved to a better technique than other existing techniques.

关键词： Deep learning optimization algorithm signal conducting system schizophrenia convolutional neural network mayfly optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Analysis of Symmetric Cryptographical Algorithms in Real Time File Transfer Communication

Analysis of Symmetric Cryptographical Algorithms in Real Tim...

引用

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Verma, Rajat Mishra, Sanat Kumar Shukla, Satvik Dhanda, Namrata Pranveer Singh Institute of Technology Department of Computer Science and Engineering Kanpur India Amity University Department of Computer Science and Engineering Uttar Pradesh Lucknow India

ISBN: (纸本)9798350385199

Since the dawn of internet software growth, we have resided in a digital environment fraught with cybersecurity concerns. The sophistication in today's traditional security measures is one of the primary reasons for the increasing number of cyberattacks, thus leaking sensitive data. Encryption, which involves transforming plain text into cipher text, is important for maintaining software security and preventing the unauthorized entry of probable hackers. However, it is evident that the encryption algorithms generally have a high resource requirement in terms of memory, processing time, and electricity. This paper compares ten more common used encryption algorithms: AES, Blowfish, CAST5, Camellia, ChaCha20, DES, 3DES, RC2, SEED, and SM4. There have been evaluations under different conditions: different data types and sizes and requirements for CPU time and encryption/decryption speed. The results of these simulations have pinpointed that each of the algorithms is good enough on its own to be efficient and effective, hence helping the organizations choose the more appropriate technique for their software's security. Therefore, this work importantly contributes to the field of cybersecurity as it adds posing of extensive examination on the most represented encryption algorithms and their performances in different situations. Organizations use the stringent encryption methods to secure their software and data which lessens the odds of cyberattack and data leak. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Long-term solar radiation forecasting in India using EMD, EEMD, and advanced machine learning algorithms

引用

Environmental Monitoring and Assessment 2025年第3期197卷 1-36页

作者： RajasundrapandiyanLeebanon, T. Murugan, N. S. Sakthivel Kumaresan, K. Jeyabose, Andrew Department of Electrical and Electronics Engineering TamilNadu College of Engineering Tamil Nadu Coimbatore India Department of Mechanical Engineering Park College of Engineering & Technology TamilNadu Coimbatore India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Solar radiation plays a critical role in the carbon sequestration processes of terrestrial ecosystems, making it a key factor in environmental sustainability among various renewable energy sources. This study integrates two advanced signal processing techniques—empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD)—with machine learning (ML) algorithms, including multilayer perceptron (MLP), random forest regression (RFR), support vector regression (SVR), and ridge regression, to forecast long-term solar radiation. Meteorological data spanning 13 years (2000–2012) from seven locations across India (Bhubaneswar, Chennai, Delhi, Hyderabad, Nagpur, Patna, and Trivandrum) were used for training and testing. The optimal model was identified based on performance metrics, including the highest linear correlation coefficient (R), and the lowest mean absolute error (MAE) and root mean square error (RMSE). The results indicate that EEMD integrated with ML algorithms consistently outperformed EMD-based approaches. Among the ML models evaluated, EEMD integrated with MLP achieved the best performance across all locations, with RMSE = 0.332, MAE = 0.26, and R2 = 0.99. Furthermore, a comparative analysis with previous studies demonstrated that the proposed approach provides superior accuracy, underscoring its efficacy in solar radiation forecasting. © The Author(s) 2025.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

ASMA: An Advanced Secure Messaging Application

引用

Recent Advances in computer science and Communications 2022年第5期15卷 786-793页

作者： Gupta, Ankur Prabhat, Purnendu Sharma, Arun Department of Computer Science and Engineering Model Institute of Engineering and Technology Jammu India

Background: User-generated digital content, typically from mobile devices, can be of a personal nature. There have been several instances in which this personal content, including but not limited to, photographs, videos, messages and personal information, has been misused by the recipients. The misuse has ranged from violating privacy through unauthorized sharing to manipulating/modifying the original content and finally forgery and fraud. Objectives: The study aims to create an Advanced Secure Messaging Application (ASMA), allowing personal digital content to be shared across mobile devices in a secure, controlled and privacy-preserving manner. The application allows the user to explicitly specify a micro-policy to control the way digital content sent by the user, is consumed, shared or modified by the recipient(s). The users should be able to check the veracity of a shared news item besides controlling group formation and enforcing content sharing guidelines within a group. Methods: A micro-policy based novel mechanism is introduced for exercising fine-grained control over the manner in which digital content generated by users is shared and distributed among their contacts. Fact-checking is supported by cross-checking the message content against credible news sources. Results: Measurements of message throughput show a consistent and manageable overhead, due to a per-message micro-policy travelling with the message data compared to traditional message sharing applications. The high user-ratings received from users in a pilot test establish acceptance of the app and the need for its advanced features. Moreover, the overheads in implementing additional security features are imperceptible at the user level. Conclusion: ASMA is a highly secure and privacy-preserving messaging application, as demonstrated by experimental results and the pilot usability study. It offers novel security and content control features, which are not available in existing mobile messaging appl

关键词： Digital devices

来源：评论

学校读者我要写书评

暂无评论

Navigating the global stock market: correlation, prediction, and the influence of external factors

引用

Iran Journal of computer science 2024年第3期7卷 397-422页

作者： Islam, Mohammad Shariful Rony, Mohammad Abu Tareq Computer Science and Telecommunication Engineering (CSTE) Noakhali Science and Technology University Noakhali 3814 Bangladesh Department of Statistics Noakhali Science and Technology University Noakhali 3814 Bangladesh

Assessing a country’s economic health is a complex task that involves predicting stock price movements. The prices of stocks reflect the overall business climate and the performance of companies. This study examines the relationship between external factors such as weather conditions and pandemic-related data during COVID-19 and global stock prices to enhance comprehension of how worldwide occurrences impact the stock exchange. The analysis reveals that external factors influence stock prices differently, but correlations can provide valuable insights into market dynamics. The research focuses on daily time-series data for various stock indices, including NYSE COMPOSITE, TSX Composite, Nikkei 225, Global X DAX Germany, and HANG SENG INDEX, as well as weather and COVID-19 data. By identifying characteristics that can be correlated with financial market data, the study finds that some factors derived from COVID-19 and weather data have a strong and moderate correlation with daily stock prices. However, it’s important to note that correlation does not necessarily imply causation, even though these insights can be helpful to investors and researchers. For this, the study employs various machine learning and deep learning models to gain a deeper understanding of stock market dynamics in the context of global events. Linear Regression is identified as the top-performing model for NYSE COMPOSITE and TSX Composite in Canada, as well as Germany’s DAX index, with exceptional predictive accuracy. Gradient Boosting Regression proves effective for Japan’s Nikkei 225 index and China’s Hang Seng Index. These findings can be valuable tools for financial analysts and investors who want to enhance their predictive abilities. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： External factors Pandemic effect Price prediction Stocks Weather

来源：评论

学校读者我要写书评

暂无评论

Automated Bengali Sign Language Character Classification with Deep Learning Techniques 15

Automated Bengali Sign Language Character Classification wit...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Akter, Tahmina Mahmud, Tanjim Barua, Tikle Naher, Sultana Rokeya Hossain, Mohammad Shahadat Andersson, Karl Port City International University Dept. of Computer Science and Engineering Chittagong Bangladesh Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati4500 Bangladesh University of Information Technology and Sciences Dept. of Computer Science and Engineering Dhaka Bangladesh University of Chittagong Dept. of Computer Science and Engineering Chittagong4331 Bangladesh Luleå University of Technology Cybersecurity Laboratory Luleå97187 Sweden

ISBN: (纸本)9798350370249

Recognition of Bengali sign language characters is crucial for facilitating communication for the deaf and hard-of-hearing population in Bengali-speaking regions, which encompass approximately 430 million people worldwide. Despite the significant number of individuals requiring this support, research on Bengali sign language character recognition remains underdeveloped. This article presents a novel approach to categorize Bengali sign language characters using the Ishara-Lipi dataset, based on convolutional neural networks (CNNs) and pretrained models. We evaluated our approach using metrics such as accuracy, precision, recall, F1-score, and confusion matrices. Our findings indicate that the CNN model achieved the highest performance with an accuracy of 98%, followed by VGG19 with 94% and ResNet variants achieving around 88%. The proposed model demonstrates robust and efficient classification capabilities, significantly bridging the gap in existing literature. This study holds substantial promise for enhancing assistive technology, thereby improving social inclusion and quality of life for Bengalispeaking deaf and hard-of-hearing individuals. © 2024 IEEE.

关键词： Bengali sign language CNNs Deaf and hard-of-hearing community Image classification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：